majentik/Voxtral-Mini-3B-2507-TurboQuant-MLX-2bit
026
Card accuracy pass 2: remove unmeasured speed claims, honest brand labels
Card accuracy sweep: honest brand labeling, remove dead links, upstream KV tip
docs: upstream-first KV-cache guidance (q8_0/q4_0, mainline Hadamard rotation); fork demoted to experimental
chore(card): add hardware compatibility section
chore(card): enrich YAML frontmatter (pipeline_tag, language, library_name, inference)
Add MLX quantized model
initial commit
